Merge tag 'xfs-4.11-fixes-1' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs fixes from Darrick Wong:
 "Here are some bug fixes for -rc2 to clean up the copy on write
  handling and to remove a cause of hangs.

   - Fix various iomap bugs

   - Fix overly aggressive CoW preallocation garbage collection

   - Fixes to CoW endio error handling

   - Fix some incorrect geometry calculations

   - Remove a potential system hang in bulkstat

   - Try to allocate blocks more aggressively to reduce ENOSPC errors"

* tag 'xfs-4.11-fixes-1' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  xfs: try any AG when allocating the first btree block when reflinking
  xfs: use iomap new flag for newly allocated delalloc blocks
  xfs: remove kmem_zalloc_greedy
  xfs: Use xfs_icluster_size_fsb() to calculate inode alignment mask
  xfs: fix and streamline error handling in xfs_end_io
  xfs: only reclaim unwritten COW extents periodically
  iomap: invalidate page caches should be after iomap_dio_complete() in direct write

14 files changed, 103 insertions, 100 deletions

diff --git a/fs/iomap.c b/fs/iomap.c
index 3ca1a8e44135..141c3cd55a8b 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -846,7 +846,8 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
         struct address_space *mapping = iocb->ki_filp->f_mapping;
         struct inode *inode = file_inode(iocb->ki_filp);
         size_t count = iov_iter_count(iter);
-        loff_t pos = iocb->ki_pos, end = iocb->ki_pos + count - 1, ret = 0;
+        loff_t pos = iocb->ki_pos, start = pos;
+        loff_t end = iocb->ki_pos + count - 1, ret = 0;
         unsigned int flags = IOMAP_DIRECT;
         struct blk_plug plug;
         struct iomap_dio *dio;
@@ -887,12 +888,12 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
         }
 
         if (mapping->nrpages) {
-                ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end);
+                ret = filemap_write_and_wait_range(mapping, start, end);
                 if (ret)
                         goto out_free_dio;
 
                 ret = invalidate_inode_pages2_range(mapping,
-                                iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
+                                start >> PAGE_SHIFT, end >> PAGE_SHIFT);
                 WARN_ON_ONCE(ret);
                 ret = 0;
         }
@@ -941,6 +942,8 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
                 __set_current_state(TASK_RUNNING);
         }
 
+        ret = iomap_dio_complete(dio);
+
         /*
          * Try again to invalidate clean pages which might have been cached by
          * non-direct readahead, or faulted in by get_user_pages() if the source
@@ -949,12 +952,12 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
          * this invalidation fails, tough, the write still worked...
          */
         if (iov_iter_rw(iter) == WRITE && mapping->nrpages) {
-                ret = invalidate_inode_pages2_range(mapping,
-                                iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
-                WARN_ON_ONCE(ret);
+                int err = invalidate_inode_pages2_range(mapping,
+                                start >> PAGE_SHIFT, end >> PAGE_SHIFT);
+                WARN_ON_ONCE(err);
         }
 
-        return iomap_dio_complete(dio);
+        return ret;
 
 out_free_dio:
         kfree(dio);
diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c
index 2dfdc62f795e..70a5b55e0870 100644
--- a/fs/xfs/kmem.c
+++ b/fs/xfs/kmem.c
@@ -25,24 +25,6 @@
 #include "kmem.h"
 #include "xfs_message.h"
 
-/*
- * Greedy allocation.  May fail and may return vmalloced memory.
- */
-void *
-kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize)
-{
-        void            *ptr;
-        size_t          kmsize = maxsize;
-
-        while (!(ptr = vzalloc(kmsize))) {
-                if ((kmsize >>= 1) <= minsize)
-                        kmsize = minsize;
-        }
-        if (ptr)
-                *size = kmsize;
-        return ptr;
-}
-
 void *
 kmem_alloc(size_t size, xfs_km_flags_t flags)
 {
diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h
index 689f746224e7..f0fc84fcaac2 100644
--- a/fs/xfs/kmem.h
+++ b/fs/xfs/kmem.h
@@ -69,8 +69,6 @@ static inline void  kmem_free(const void *ptr)
 }
 
 
-extern void *kmem_zalloc_greedy(size_t *, size_t, size_t);
-
 static inline void *
 kmem_zalloc(size_t size, xfs_km_flags_t flags)
 {
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index a9c66d47757a..9bd104f32908 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -763,8 +763,8 @@ xfs_bmap_extents_to_btree(
                 args.type = XFS_ALLOCTYPE_START_BNO;
                 args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
         } else if (dfops->dop_low) {
-try_another_ag:
                 args.type = XFS_ALLOCTYPE_START_BNO;
+try_another_ag:
                 args.fsbno = *firstblock;
         } else {
                 args.type = XFS_ALLOCTYPE_NEAR_BNO;
@@ -790,13 +790,17 @@ try_another_ag:
         if (xfs_sb_version_hasreflink(&cur->bc_mp->m_sb) &&
             args.fsbno == NULLFSBLOCK &&
             args.type == XFS_ALLOCTYPE_NEAR_BNO) {
-                dfops->dop_low = true;
+                args.type = XFS_ALLOCTYPE_FIRST_AG;
                 goto try_another_ag;
         }
+        if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
+                xfs_iroot_realloc(ip, -1, whichfork);
+                xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+                return -ENOSPC;
+        }
         /*
          * Allocation can't fail, the space was reserved.
          */
-        ASSERT(args.fsbno != NULLFSBLOCK);
         ASSERT(*firstblock == NULLFSBLOCK ||
                args.agno >= XFS_FSB_TO_AGNO(mp, *firstblock));
         *firstblock = cur->bc_private.b.firstblock = args.fsbno;
@@ -4150,6 +4154,19 @@ xfs_bmapi_read(
         return 0;
 }
 
+/*
+ * Add a delayed allocation extent to an inode. Blocks are reserved from the
+ * global pool and the extent inserted into the inode in-core extent tree.
+ *
+ * On entry, got refers to the first extent beyond the offset of the extent to
+ * allocate or eof is specified if no such extent exists. On return, got refers
+ * to the extent record that was inserted to the inode fork.
+ *
+ * Note that the allocated extent may have been merged with contiguous extents
+ * during insertion into the inode fork. Thus, got does not reflect the current
+ * state of the inode fork on return. If necessary, the caller can use lastx to
+ * look up the updated record in the inode fork.
+ */
 int
 xfs_bmapi_reserve_delalloc(
         struct xfs_inode        *ip,
@@ -4236,13 +4253,8 @@ xfs_bmapi_reserve_delalloc(
         got->br_startblock = nullstartblock(indlen);
         got->br_blockcount = alen;
         got->br_state = XFS_EXT_NORM;
-        xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got);
 
-        /*
-         * Update our extent pointer, given that xfs_bmap_add_extent_hole_delay
-         * might have merged it into one of the neighbouring ones.
-         */
-        xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *lastx), got);
+        xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got);
 
         /*
          * Tag the inode if blocks were preallocated. Note that COW fork
@@ -4254,10 +4266,6 @@ xfs_bmapi_reserve_delalloc(
         if (whichfork == XFS_COW_FORK && (prealloc || aoff < off || alen > len))